feat(analysis): make OCR the active backend, keep vision dormant

The worker now always dispatches through the in-process ocrs engine.
`AnalysisConfig::effective_backend()` returns Ocr regardless of the
parsed `ANALYSIS_BACKEND` (warning if `vision` was requested), and
`spawn_analysis_daemon` selects on it. The vision dispatcher, client,
and readiness probe stay compiled and intact behind the unreachable
match arm, so re-enabling is a one-line change.

The startup-reclaim regression test no longer leaned on the vision arm
to skip model loading; it now points the engine at a missing model path
and asserts the orphaned lease is still reclaimed before the (failing)
engine build — proving reclaim runs independently of engine readiness.

Also gitignore backend/models/*.rten so locally-downloaded ocrs models
for native `cargo run` aren't committed.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/.gitignore

@@ -1,3 +1,7 @@
 /target
 /.sqlx
 .env
+
+# Local OCR models for native dev (downloaded, not source)
+models/
+*.rten

backend/src/app.rs

@@ -434,7 +434,7 @@ async fn spawn_analysis_daemon(
     let (dispatcher, readiness): (
         Arc<dyn crate::analysis::daemon::AnalyzeDispatcher>,
         Option<Arc<dyn crate::analysis::daemon::VisionReadiness>>,
-    ) = match cfg.backend {
+    ) = match cfg.effective_backend() {
         crate::config::AnalysisBackend::Ocr => {
             // Load the `.rten` models once; a bad path is a loud boot error.
             let engine = crate::analysis::ocr::OcrsEngine::from_model_paths(
@@ -1473,29 +1473,30 @@ mod tests {
         // Bind to a local so the TempDir lives for the rest of the test.
         // `tempfile::tempdir().unwrap().path()` would drop the TempDir
         // at end-of-expression and `LocalStorage` would hold a path to
-        // a deleted directory. (Today this is fine because the dispatch
+        // a deleted directory.
-        // fails before storage is touched, but it makes the test fragile
-        // to any future code rearrangement.)
         let storage_dir = tempfile::tempdir().unwrap();
         let storage: Arc<dyn Storage> =
             Arc::new(LocalStorage::new(storage_dir.path()));
         let mut cfg = crate::config::AnalysisConfig::default();
-        // Use the vision backend so the daemon doesn't try to load the ocrs
+        // The worker always runs OCR now (vision is dormant — see
-        // `.rten` models (absent in unit CI). This test only exercises the
+        // `effective_backend`), and the `.rten` models aren't shipped to unit
-        // pre-worker lease reclaim, which is engine-agnostic; no dispatch runs.
+        // CI. Point the engine at a path that can't exist so the *engine build*
-        cfg.backend = crate::config::AnalysisBackend::Vision;
+        // fails deterministically. Reclaim runs at the very top of
+        // `spawn_analysis_daemon`, before — and independently of — engine
+        // readiness, so the row must still be reclaimed even though spawn
+        // returns Err. That's exactly the regression this test guards (an
+        // analysis-only deploy must reclaim orphaned leases at startup).
+        cfg.ocr_detection_model = "/nonexistent/text-detection.rten".to_string();
+        cfg.ocr_recognition_model = "/nonexistent/text-recognition.rten".to_string();
         cfg.workers = 1;
         cfg.job_timeout = Duration::from_secs(1);
         let events = Arc::new(crate::analysis::events::AnalysisEvents::new());
 
-        let handle = spawn_analysis_daemon(pool.clone(), storage, &cfg, events)
+        let spawned = spawn_analysis_daemon(pool.clone(), storage, &cfg, events).await;
-            .await
+        assert!(
-            .expect("spawn");
+            spawned.is_err(),
-        // Immediately shut down — we're only here to prove reclaim ran.
+            "engine build must fail with a missing model path"
-        // The workers may briefly pick up the now-pending row; that's
+        );
-        // fine, but we cancel before any real dispatch (the LocalStorage
-        // key doesn't exist, so a dispatch would fail anyway).
-        handle.shutdown().await;
 
         // The reclaim must have moved the row back to pending with the
         // attempt refunded (attempts goes from 1 → 0). Reaching it on the

backend/src/config.rs

@@ -262,6 +262,24 @@ impl Default for AnalysisConfig {
 }
 
 impl AnalysisConfig {
+    /// The backend the worker actually dispatches through.
+    ///
+    /// Vision is **temporarily disabled**: the engine code (`analysis::vision`,
+    /// `RealAnalyzeDispatcher`, the readiness probe) is kept intact but never
+    /// selected. Until it's re-enabled, this returns [`AnalysisBackend::Ocr`]
+    /// regardless of the parsed `backend`, logging a warning if `vision` was
+    /// requested so an env override isn't silently ignored. Re-enabling vision
+    /// is then a one-line change here (return `self.backend`).
+    pub fn effective_backend(&self) -> AnalysisBackend {
+        if self.backend == AnalysisBackend::Vision {
+            tracing::warn!(
+                "ANALYSIS_BACKEND=vision requested but the vision backend is temporarily \
+                 disabled; running OCR instead"
+            );
+        }
+        AnalysisBackend::Ocr
+    }
+
     pub fn from_env() -> Self {
         let d = AnalysisConfig::default();
         Self {
@@ -840,6 +858,19 @@ mod tests {
         assert_eq!(AnalysisConfig::from_env().backend, AnalysisBackend::Ocr);
     }
 
+    #[test]
+    fn effective_backend_is_ocr_even_when_vision_requested() {
+        // Vision is temporarily disabled: the worker always runs OCR no matter
+        // what `ANALYSIS_BACKEND` parsed to. `backend` still reflects the raw
+        // request (so the override is visible/loggable), but `effective_backend`
+        // is the value the daemon actually dispatches through.
+        let mut cfg = AnalysisConfig::default();
+        cfg.backend = AnalysisBackend::Vision;
+        assert_eq!(cfg.effective_backend(), AnalysisBackend::Ocr);
+        cfg.backend = AnalysisBackend::Ocr;
+        assert_eq!(cfg.effective_backend(), AnalysisBackend::Ocr);
+    }
+
     #[test]
     fn ocr_model_paths_parse_from_env() {
         let _g = ENV_GUARD.lock().unwrap_or_else(|p| p.into_inner());